Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ేష
    -0.09
    essaan
    -0.08
    Cours
    -0.08
     ენ
    -0.08
     latt
    -0.08
     lattice
    -0.08
     ուս
    -0.08
     կրթ
    -0.08
    elings
    -0.08
     Anh
    -0.08
    POSITIVE LOGITS
     pharmac
    0.08
     psychedelic
    0.08
     cough
    0.07
    auw
    0.07
     hilar
    0.07
    LOCAL
    0.07
     LOCAL
    0.07
     dear
    0.07
    Про
    0.07
    .Footer
    0.06
    Act Density 0.000%

    No Known Activations